Research map / Learning theory and algorithms / Sample complexity
Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use PPE to privatize an existing non-private GMM parameter learner | GMM parameter learning without boundedness assumptions · Unbounded GMM parameter learning | sample complexity: O(m_{\textsc{non-private}}(\gamma, \beta/2t, k, d)\log(1/\delta) / \varepsilon) | Helped |
| Use PPE to privatize an existing non-private GMM parameter learner | GMM parameter learning without boundedness assumptions · Unbounded GMM parameter learning | running time: O((\log(1/\delta) / \varepsilon)\cdot T_{\mathcal{A}} + (\log(1/\delta) / \varepsilon)^2 \cdot (k^2 d^3 + k^3 \log k) ) | Helped |
| Randomly permute masked mixture components | GMM masking mechanism · GMM parameter masking | privacy under component reordering | Helped |
| Select one close solution instead of aggregating clustered learner outputs | Private populous estimator · GMM parameter learning | ability to handle component-order ambiguity | Helped |
| Reduce permutation-invariant mixture distance computation to bipartite matching | GMM component matching · GMM distance computation | running time: O(k^2 T_{\dist} + k^3 \log k) | Helped |
Closest papers by meaning
- Sample-Efficient Private Learning of Mixtures of Gaussians (NeurIPS 2024 · similarity 0.93)
- On Learning Parallel Pancakes with Mostly Uniform Weights (ICML 2025 · similarity 0.87)
- Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters (NeurIPS 2026 · similarity 0.87)
- Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models (NeurIPS 2024 · similarity 0.87)
- Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions? (NeurIPS 2026 · similarity 0.86)
- Public-data Assisted Private Stochastic Optimization: Power and Limitations (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.